(28 days)
The GI Genius™ system is a computer-assisted reading tool designed to aid endoscopists in detecting colonic mucosal lesions (such as polyps and adenomas) in real time during standard white-light endoscopy examinations of patients undergoing screening and surveillance endoscopic mucosal evaluations. The GI Genius™ computer-assisted detection device is limited for use with standard white-light endoscopy imaging only. This device is not intended to replace clinical decision making.
GI Genius is an artificial intelligence-based device that has been trained to process colonoscopy images containing regions consistent with colorectal lesions like polyps, including those with flat (non-polypoid) morphology.
GI Genius is composed of software (namely, ColonPRO™ 4.0) and hardware (namely, GI Genius™ Module 100 and 200).
GI Genius™ Module 100 and 200 are compatible with Video Processors featuring SDI (SMPTE 259M) or HD-SDI (SMPTE 292M) output ports and endoscopic display monitors featuring SDI (SMPTE 259M) or HD-SDI (SMPTE 292M) input ports. GI Genius™ Module 200 is also compatible with Video Processors featuring the 4K UHD standard.
The GI Genius system is connected between the video processor and the endoscopic display monitor. When first switched on, the endoscopic field of view is clearly identified by four corner markers, and a blinking green square indicator appears on the connected endoscopic display monitor to state that the system is ready to function.
During live video streaming of the endoscopic video image, GI Genius generates a video output on the endoscopic display monitor that contains the original live video together with superimposed green square markers that will appear when a polyp or other lesion of interest is detected, accompanied by a short sound. These markers will not be visible when no lesion detection occurs.
The operating principle of the subject device is identical to that of the predicate device, this being a computerassisted detection device used in conjunction with endoscopy for the detection of abnormal lesions in the gastrointestinal tract. This device with advanced software algorithms brings attention to images to aid in the detection of lesions. The device includes hardware to support interfacing with video endoscopy systems and the accessories given by the footswitch and the USB K-switch.
Here's an analysis of the acceptance criteria and study information for the GI Genius™ Module 100, GI Genius™ Module 200, and ColonPRO™ 4.0, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document doesn't explicitly state "acceptance criteria" for each performance metric, but it does present a comparison table that shows the performance of the Subject Device (ColonPRO™ 4.0) against its Predicate Device (GI Genius™ System 100 and 200). The implication is that the subject device's performance, being "improved" or "same" compared to the already cleared predicate, meets the necessary equivalence for clearance.
| Characteristic | Acceptance Criteria (Implied: at least as good as predicate) | Reported Device Performance (Subject Device - ColonPRO™ 4.0) | Comparison to Predicate (Performance of Predicate) |
|---|---|---|---|
| Lesion-based sensitivity | ≥ 86.5% | 88.07 % | Improved (86.5 %) |
| Frame-level True Positive | ≥ 269,223 | 277,738 | Improved (269,223) |
| Frame-level True Negative | For 150 videos/338 polyps: ≥ 5,239,128 | 5,248,406 | Improved (5,239,128) |
| Frame-level False Positive | For 150 videos/338 polyps: ≤ 104,669 | 95,391 | Improved (104,669) |
| Frame-level False Negative | For 150 videos/338 polyps: ≤ 192,567 | 184,052 | Improved (192,567) |
| True positive rate per frame | Mean: ≥ 58.30 %, % of polyps: 100 % | Mean: 60.14 %, % of polyps: 100 % | Improved (Mean: 58.30 %, % of polyps: 100 %) |
| False positive rate per frame | Mean: ≤ 1.96 % | Mean: 1.79 % | Improved (Mean: 1.96 %) |
| Frame-Based TPr/FPr ROC curve, AUC | ≥ 0.796 | 0.826 | Improved (0.796) |
| False positive clusters per patient | 500 ms: ≤ 11 | 500 ms: 10 | Improved ( 500 ms: 11) |
| Video delay, signal in to signal out | As per predicate (1.52 µs for Module 100, 0.74 µs for Module 200) | 1.52 µs (Module 100), 0.74 µs (Module 200) | Same |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: The document explicitly states the frame-level performance was assessed using 150 videos / 338 polyps. It doesn't specify if this refers to the number of patients or individual lesions.
- Data Provenance: The document does not provide information on the country of origin of the data or whether it was retrospective or prospective. It only mentions that "the baseline clinical validation for the subject device was conducted and reviewed in DEN200055 and is still applicable." Since this is a Special 510(k) for a software update (version 4.0.0 replacing 3.0.2), the primary performance data seems to derive from the re-training of the neural network rather than a new clinical study. The "Non-clinical testing" section mentions that "Tests according to the Standalone Performance Testing Protocol v2.0, submitted as part of the K231143 predicate device submission, have been repeated for the applicable parts of the subject device." This suggests the test set for this submission is the same as, or comparable to, that used for the predicate.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not specify the number of experts used or their qualifications for establishing the ground truth on the test set.
4. Adjudication Method for the Test Set
The document does not specify the adjudication method used for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The document does not mention or present an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. The device is described as a "computer-assisted reading tool," suggesting it's intended to work alongside an endoscopist, but no study on human performance improvement with the device is provided in this submission or summary. It refers to the "baseline clinical validation" for the predicate device, but the details of that validation are not present here.
6. Standalone Performance Study (Algorithm Only)
Yes, a standalone performance study was done. The performance metrics listed in the table (Lesion-based sensitivity, Frame-level True Positive/Negative/False Positive/Negative, True positive rate per frame, False positive rate per frame, Frame-Based TPr/FPr ROC curve, AUC, False positive clusters per patient) all refer to the algorithm's performance without direct human-in-the-loop interaction for the purpose of these specific measurements. The "Non-clinical testing" section explicitly states: "Tests according to the Standalone Performance Testing Protocol v2.0, submitted as part of the K231143 predicate device submission, have been repeated for the applicable parts of the subject device."
7. Type of Ground Truth Used
The document implies the ground truth for polyps and lesions was used to evaluate detection performance. However, it does not explicitly state the method for establishing this ground truth (e.g., expert consensus, pathology, outcome data). Likely, for lesion detection in endoscopic videos, ground truth would typically be established by expert endoscopist review, potentially confirmed by pathology for detected lesions.
8. Sample Size for the Training Set
The document does not specify the sample size for the training set. It only mentions "retraining of the neural network" as the source of improved detection performance for ColonPRO™ 4.0.
9. How the Ground Truth for the Training Set Was Established
The document does not specify how the ground truth for the training set was established.
§ 876.1520 Gastrointestinal lesion software detection system.
(a)
Identification. A gastrointestinal lesion software detection system is a computer-assisted detection device used in conjunction with endoscopy for the detection of abnormal lesions in the gastrointestinal tract. This device with advanced software algorithms brings attention to images to aid in the detection of lesions. The device may contain hardware to support interfacing with an endoscope.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, including detection of gastrointestinal lesions and evaluation of all adverse events.
(2) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. Testing must include:
(i) Standalone algorithm performance testing;
(ii) Pixel-level comparison of degradation of image quality due to the device;
(iii) Assessment of video delay due to marker annotation; and
(iv) Assessment of real-time endoscopic video delay due to the device.
(3) Usability assessment must demonstrate that the intended user(s) can safely and correctly use the device.
(4) Performance data must demonstrate electromagnetic compatibility and electrical safety, mechanical safety, and thermal safety testing for any hardware components of the device.
(5) Software verification, validation, and hazard analysis must be provided. Software description must include a detailed, technical description including the impact of any software and hardware on the device's functions, the associated capabilities and limitations of each part, the associated inputs and outputs, mapping of the software architecture, and a description of the video signal pipeline.
(6) Labeling must include:
(i) Instructions for use, including a detailed description of the device and compatibility information;
(ii) Warnings to avoid overreliance on the device, that the device is not intended to be used for diagnosis or characterization of lesions, and that the device does not replace clinical decision making;
(iii) A summary of the clinical performance testing conducted with the device, including detailed definitions of the study endpoints and statistical confidence intervals; and
(iv) A summary of the standalone performance testing and associated statistical analysis.